自适应融合层级特征的混合退化图像复原算法

多种退化类型混合的图像比单一类型的退化图像降质更严重,很难建立精确模型对其复原,研究端到端的神经网络算法是复原的关键.现有的基于操作选择注意力网络的算法(operation-wiseattentionnetwork,OWAN)虽然有一定的性能提升,但是其网络过于复杂,运行较慢,复原图像缺乏高频细节,整体效果也有提升的空间.针对这些问题,提出一种基于层级特征融合的自适应复原算法.该算法直接融合不同感受野分支的特征,增强复原图像的结构;用注意力机制对不同层级的特征进行动态融合,增加模型的自适应性,降低了模型冗余;另外,结合L1损失和感知损失,增强了复原图像的视觉感知效果.在DIV2K,BSD500等数据集上的实验结果表明,该算法无论是在峰值信噪比和结构相似性上的定量分析,还是在主观视觉质量方面,均优于OWAN算法,充分证明了该算法的有效性.     

Adaptive compensation of persistent actuator failures of nonlinear systems

In this article, adaptive compensation designs are developed for nonlinear systems with uncertainties from the system functions and persistent actuator failures of characterizations that (i) some unknown system inputs are stuck at some unknown fixed or varying values at unknown time instants and (ii) the failure pattern always switches from one to another and the switching does not stop. Such a controlled plant is described by an uncertain time-varying nonlinear system, and some robust adaptive feedback linearization based failure compensation results are studied for closed-loop system stabilization and bounded output tracking for some specific conditions. To improve the tracking performance in the presence of persistent actuator failures, a new adaptive control scheme is developed, using the failure indicator function which contains the failure pattern and failure time in the formulation. Detailed stability and tracking performance are shown. Simulation results are shown to verify the effectiveness of the proposed adaptive actuator failure compensation method.     

Adaptive finite-time tracking control for parameterized nonlinear systems with full state constraints

In this article, the issue of adaptive finite-time dynamic surface control (DSC) is discussed for a class of parameterized nonlinear systems with full state constraints. Using the property of logarithmic function, a one-to-one nonlinear mapping is constructed to transform a constrained system into an unconstrained system with the same structure. The nonlinear filter is constructed to replace the first-order linear filter in the traditional DSC, and the demand on the filter time constant is reduced. Based on finite-time stable theory and using modified DSC, the finite-time controller is designed via DSC. Theoretical analysis shows that all the signals in the closed-loop system are semiglobal practical finite-time stable. Furthermore, none of the states are outside the defined open set. In the end, simulation results are presented to demonstrate the effectiveness of the proposed control schemes with both linear filters and nonlinear filters.     

Mixture ratio modeling of dynamic systems

Any knowledge extraction relies (possibly implicitly) on a hypothesis about the modelled-data dependence. The extracted knowledge ultimately serves to a decision-making (DM). DM always faces uncertainty and this makes probabilistic modelling adequate. The inspected black-box modeling deals with “universal” approximators of the relevant probabilistic model. Finite mixtures with components in the exponential family are often exploited. Their attractiveness stems from their flexibility, the cluster interpretability of components and the existence of algorithms for processing high-dimensional data streams. They are even used in dynamic cases with mutually dependent data records while regression and auto-regression mixture components serve to the dependence modeling. These dynamic models, however, mostly assume data-independent component weights, that is, memoryless transitions between dynamic mixture components. Such mixtures are not universal approximators of dynamic probabilistic models. Formally, this follows from the fact that the set of finite probabilistic mixtures is not closed with respect to the conditioning, which is the key estimation and predictive operation. The paper overcomes this drawback by using ratios of finite mixtures as universally approximating dynamic parametric models. The paper motivates them, elaborates their approximate Bayesian recursive estimation and reveals their application potential.     

Adaptive actuator failure compensation for cooperative robotic manipulators with parameter uncertainties

This article develops a new framework of adaptive actuator failure compensation control for cooperative manipulator systems with parameter uncertainties in addition to actuator failures, and designs and analyzes effective actuator failure compensation schemes for such robotic systems. The new adaptive control design uses an integration of multiple individual failure compensators and direct adaptation to handle various types of uncertainties in such robotic systems. The design can also be used for concurrent actuator failure cases, to expand the capability of adaptive actuator failure compensation. With a complete proof and performance analysis, it is shown that the proposed control scheme guarantees the desired closed-loop stability and asymptotic output tracking, despite actuator failures whose patterns, time instants and values are all unknown. Simulation results of a benchmark cooperative manipulator system are presented to verify the desired control performance of the system with both typical constant and square-wave actuator failure signals.     

Adaptive constraint control for flexible manipulator systems modeled by partial differential equations with dead-zone input

In this article, based on partial differential equations (PDEs), the flexible manipulator system with both dead-zone input and state constraints is studied. The dynamic model of the flexible manipulator system is described by PDEs. The parameters of the dead-zone input are unknown, and the state constraint problem is also considered. An adaptive approach is proposed to offset the effects caused by dead-zone input. Thus, to guarantee that all states remain within their respective constraint regions, the boundary control law based on the barrier Lyapunov function is given, and an adaptive controller is designed. According to the Lyapunov analysis method, the control method is given to ensure that all signals of the closed-loop system are bounded and all states satisfy the constraint conditions. Finally, simulation results show the effectiveness of the proposed control method in this article.     

The effectiveness of adaptive versus non-adaptive learning with digital educational games

For the training of academic skills, digital educational games with integrated adaptivity are promising. Adaptive games are considered superior to non-adaptive games, because they constantly assess children's performance, and accordingly adapt the difficulty of the tasks corresponding to the children's individual level. However, empirical evidence with regard to the effectivity of adaptive compared to non-adaptive games is limited. A study was conducted with 191 children from the third year of Kinder garten who were enrolled in one of three conditions, that is, playing an adaptive version of the reading game (RG), a non-adaptive version of the RG or training with pen-and-paper exercises. In all three conditions, children trained emergent reading (phonological awareness and letter knowledge) once a week for 30 min over a period of 5 weeks. Children's performance on cognitive (phonological awareness, letter knowledge, reading fluency) and non-cognitive (motivation, self-concept) factors was assessed. Results revealed a significant improvement in phonological awareness and letter knowledge in all conditions. However, no differences between the conditions were observed with respect to children's improvement on phonological awareness and letter knowledge or on their post-test scores for reading fluency. With regard to motivation and self-concept, again, no differences in these non-cognitive factors were observed across conditions.     

Clustering adaptive canonical correlations for high-dimensional multi-modal data

Multi-modal canonical correlation analysis (MCCA) is an important joint dimension reduction method and has been widely applied to clustering tasks of multi-modal data. MCCA-based clustering is usually dimension reduction of high-dimensional data followed by clustering of low-dimensional data. However, the two-stage clustering is difficult to ensure the adaptability of dimension reduction and clustering, which will affect the final clustering performance. To solve the issue, we propose a novel clustering adaptive multi-modal canonical correlations (CAMCCs) method, which constructs a unified optimization model of multi-modal correlation learning and clustering. The method not only realizes discriminant learning of correlation projection directions under unsupervised cases, but also is able to directly obtain class labels of multi-modal data. Additionally, the method also realizes out-of-sample extension in class labels. Solutions of CAMCCs are optimized by an iterative way, and we analyze its convergence. Extensive experimental results on various datasets have demonstrated the effectiveness of the method.     

Passivity and synchronisation of complex dynamical networks with multiple derivative couplings

Two network models with multiple derivative couplings and different dimensions of output and input vectors are investigated in this paper. The problem of passivity for the proposed network models is analysed by utilising some inequality techniques and Lyapunov functional method, and several synchronisation conditions for complex dynamical networks with multiple derivative couplings (CDNMDC) are given. Moreover, by employing adaptive state feedback control strategy, some sufficient conditions for guaranteeing passivity and synchronisation of CDNMDC are obtained. In the end, we give two examples to verify the effectiveness of the results.     

煤矿智能化开采关键技术分析

煤矿智能化开采是中国煤炭工业技术发展的必经之路,是煤矿企业进一步发展的主要目标。通过阐述智能化的概念,介绍了煤矿智能化开采的定义和系统构成,分析了煤矿智能化开采的关键技术,包括工作面综采装备位姿监测技术、围岩-装备耦合自适应控制技术、综采装备核心智能控制技术和矿井机器人技术。针对各关键技术问题进行分析,提出相应的解决方案和核心装备智能化控制逻辑。通过解决煤矿智能化开采过程中的关键技术问题,加快煤矿企业智能化改革,确保企业稳定、可持续发展。